Do machine learning techniques outperform autoregressive distributed lag models in inflation forecasting?

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28160%2F25%3A63598618" target="_blank" >RIV/70883521:28160/25:63598618 - isvavai.cz</a>

Result on the web

<a href="https://pep.vse.cz/artkey/pep-202504-0003_do-machine-learning-techniques-outperform-autoregressive-distributed-lag-models-in-inflation-forecasting.php" target="_blank" >https://pep.vse.cz/artkey/pep-202504-0003_do-machine-learning-techniques-outperform-autoregressive-distributed-lag-models-in-inflation-forecasting.php</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18267/j.pep.898" target="_blank" >10.18267/j.pep.898</a>

Result language

angličtina

Original language name

Do machine learning techniques outperform autoregressive distributed lag models in inflation forecasting?

Original language description

Following the COVID-19 pandemic, Romania and other Central and Eastern European (CEE) countries faced some of the highest inflation rates in the European Union, creating a pressing need for accurate short-term forecasts to guide monetary policy. This study compares modern machine learning (ML) methods-Long Short-Term Memory (LSTM) neural networks, Random Forests (RF) and Support Vector Regression (SVR)-with traditional Autoregressive Distributed Lag (ARDL) models in forecasting Harmonised Index of Consumer Prices. Using quarterly data for Romania (2006Q1-2023Q4) and monthly data for nine CEE economies (2006M1-2025M3), we incorporate unemployment and sentiment indicators derived from the Romanian Central Bank reports and the European Commission&apos;s Economic Sentiment Indicator (ESI). We further evaluate model performance through simulation experiments that include high persistence, moving-average non-invertibility, nonlinear regimes, and structural breaks. Across both empirical and LSTM and SVR models-they frequently deliver lower forecast errors than ARDL, with LSTM achieving up to 53% reductions in mean squared error relative to na &amp; iuml;ve benchmarks. However, ARDL remains competitive when sentiment indices are the main predictor. These findings highlight that while advanced ML models can capture nonlinear dynamics and regime changes, traditional econometric tools still provide valuable robustness, particularly in sentiment-driven contexts. Overall, integrating ML, econometric approaches, and sentiment analysis offers a more reliable toolkit for short-horizon inflation forecasting under economic uncertainty.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

50202 - Applied Economics, Econometrics

Project

—

Continuities

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Prague Economic Papers: quarterly journal of economic theory and policy

ISSN

1210-0455

e-ISSN

2336-730X

Volume of the periodical

34

Issue of the periodical within the volume

4

Country of publishing house

CZ - CZECH REPUBLIC

Number of pages

64

Pages from-to

495-558

UT code for WoS article

001648786100002

EID of the result in the Scopus database

—